Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3068 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1358. Min Range: -6.1358
Max Act: 6.1358. Min Act: -0.1700
Data Index: 6255062 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1358. Min Range: -6.1358
Max Act: 5.6358. Min Act: -0.1700
Data Index: 6255061 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1358. Min Range: -6.1358
Max Act: 5.6358. Min Act: -0.1700
Data Index: 5811949 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1358. Min Range: -6.1358
Max Act: 5.5733. Min Act: -0.1700
Data Index: 5943149 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1358. Min Range: -6.1358
Max Act: 5.6045. Min Act: -0.1700
Data Index: 3239268 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1358. Min Range: -6.1358
Max Act: 5.5733. Min Act: -0.1700
Data Index: 7905117 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1358. Min Range: -6.1358
Max Act: 5.5733. Min Act: -0.1700
Data Index: 4163166 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1358. Min Range: -6.1358
Max Act: 5.4795. Min Act: -0.1700
Data Index: 3536164 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1358. Min Range: -6.1358
Max Act: 5.4170. Min Act: -0.1700
Data Index: 7637443 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1358. Min Range: -6.1358
Max Act: 5.4170. Min Act: -0.1700
Data Index: 7637444 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1358. Min Range: -6.1358
Max Act: 5.4170. Min Act: -0.1700
Data Index: 3239267 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1358. Min Range: -6.1358
Max Act: 5.4170. Min Act: -0.1700
Data Index: 3768570 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1358. Min Range: -6.1358
Max Act: 5.3858. Min Act: -0.1700
Data Index: 2689121 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1358. Min Range: -6.1358
Max Act: 5.3858. Min Act: -0.1700
Data Index: 8793976 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1358. Min Range: -6.1358
Max Act: 5.3858. Min Act: -0.1700
Data Index: 807766 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1358. Min Range: -6.1358
Max Act: 5.3545. Min Act: -0.1700
Data Index: 3058364 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1358. Min Range: -6.1358
Max Act: 5.3545. Min Act: -0.1700
Data Index: 2896701 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1358. Min Range: -6.1358
Max Act: 5.3858. Min Act: -0.1700
Data Index: 7136480 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1358. Min Range: -6.1358
Max Act: 5.3545. Min Act: -0.1700
Data Index: 813369 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1358. Min Range: -6.1358
Max Act: 5.3545. Min Act: -0.1700
Data Index: 5179761 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #19